{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QNEQXND7AAJT35CO5XYOJLZEX6","short_pith_number":"pith:QNEQXND7","schema_version":"1.0","canonical_sha256":"83490bb47f00133df44eedf0e4af24bf9298ca04d48ddfb30ea401346a968613","source":{"kind":"arxiv","id":"2506.01938","version":1},"attestation_state":"computed","paper":{"title":"Novel Benchmark for NER in the Wastewater and Stormwater Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Franca Debole, Francesca Frontini, Franco Alberto Cardillo, Mitra Aelami, Nan\\'ee Chahinian, Serge Conrad","submitted_at":"2025-06-02T17:54:16Z","abstract_excerpt":"Effective wastewater and stormwater management is essential for urban sustainability and environmental protection. Extracting structured knowledge from reports and regulations is challenging due to domainspecific terminology and multilingual contexts. This work focuses on domain-specific Named Entity Recognition (NER) as a first step towards effective relation and information extraction to support decision making. A multilingual benchmark is crucial for evaluating these methods. This study develops a French-Italian domain-specific text corpus for wastewater management. It evaluates state-of-th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.01938","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T17:54:16Z","cross_cats_sorted":[],"title_canon_sha256":"90d4429d36d925555d206e90b32bd5eed28782d86d9a9fdab056aa1060f9dfd6","abstract_canon_sha256":"4a38dda1bc572ef804b8711f0a9b1b80d7fbb8a7423dbbcf9b9290589b743226"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:21.693867Z","signature_b64":"3mbALYoaBNUsa5YHlfmhWip4oAtkxYSan0LGFHBz2B4P/R96LUcuaJ+TUKYPsOwepz6H6NaA4EwVWwp5AphODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83490bb47f00133df44eedf0e4af24bf9298ca04d48ddfb30ea401346a968613","last_reissued_at":"2026-07-05T11:14:21.693396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:21.693396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Novel Benchmark for NER in the Wastewater and Stormwater Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Franca Debole, Francesca Frontini, Franco Alberto Cardillo, Mitra Aelami, Nan\\'ee Chahinian, Serge Conrad","submitted_at":"2025-06-02T17:54:16Z","abstract_excerpt":"Effective wastewater and stormwater management is essential for urban sustainability and environmental protection. Extracting structured knowledge from reports and regulations is challenging due to domainspecific terminology and multilingual contexts. This work focuses on domain-specific Named Entity Recognition (NER) as a first step towards effective relation and information extraction to support decision making. A multilingual benchmark is crucial for evaluating these methods. This study develops a French-Italian domain-specific text corpus for wastewater management. It evaluates state-of-th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01938","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.01938/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.01938","created_at":"2026-07-05T11:14:21.693453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01938v1","created_at":"2026-07-05T11:14:21.693453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01938","created_at":"2026-07-05T11:14:21.693453+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNEQXND7AAJT","created_at":"2026-07-05T11:14:21.693453+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNEQXND7AAJT35CO","created_at":"2026-07-05T11:14:21.693453+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNEQXND7","created_at":"2026-07-05T11:14:21.693453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNEQXND7AAJT35CO5XYOJLZEX6","json":"https://pith.science/pith/QNEQXND7AAJT35CO5XYOJLZEX6.json","graph_json":"https://pith.science/api/pith-number/QNEQXND7AAJT35CO5XYOJLZEX6/graph.json","events_json":"https://pith.science/api/pith-number/QNEQXND7AAJT35CO5XYOJLZEX6/events.json","paper":"https://pith.science/paper/QNEQXND7"},"agent_actions":{"view_html":"https://pith.science/pith/QNEQXND7AAJT35CO5XYOJLZEX6","download_json":"https://pith.science/pith/QNEQXND7AAJT35CO5XYOJLZEX6.json","view_paper":"https://pith.science/paper/QNEQXND7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01938&json=true","fetch_graph":"https://pith.science/api/pith-number/QNEQXND7AAJT35CO5XYOJLZEX6/graph.json","fetch_events":"https://pith.science/api/pith-number/QNEQXND7AAJT35CO5XYOJLZEX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNEQXND7AAJT35CO5XYOJLZEX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNEQXND7AAJT35CO5XYOJLZEX6/action/storage_attestation","attest_author":"https://pith.science/pith/QNEQXND7AAJT35CO5XYOJLZEX6/action/author_attestation","sign_citation":"https://pith.science/pith/QNEQXND7AAJT35CO5XYOJLZEX6/action/citation_signature","submit_replication":"https://pith.science/pith/QNEQXND7AAJT35CO5XYOJLZEX6/action/replication_record"}},"created_at":"2026-07-05T11:14:21.693453+00:00","updated_at":"2026-07-05T11:14:21.693453+00:00"}